© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 10-GEMMASCOPE-RES-16K
    11. 11906
    Prev
    Next
    INDEX
    Explanations

    references to programming constructs and methods used in UI frameworks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     resourceCulture
    -0.84
     nahilalakip
    -0.79
    ftagPool
    -0.79
     سكانية
    -0.76
    addCriterion
    -0.71
     propOrder
    -0.70
    CopyWith
    -0.70
    IsContent
    -0.70
     ModelExpression
    -0.67
    UnusedPrivate
    -0.66
    POSITIVE LOGITS
     MonoBehaviour
    3.90
     GetComponent
    0.60
     enx
    0.59
    prepareStatement
    0.57
    gameObject
    0.53
     initComponents
    0.51
    GetComponent
    0.48
    pyplot
    0.48
    localScale
    0.47
    
    0.47
    Activations Density 0.017%

    No Known Activations